The Agent Skills Directory

[SAFE]: Technical analysis of the provided instructions reveals they are entirely focused on the legitimate modeling and validation of business processes using the OrgScript DSL. There is no evidence of command injection, credential theft, or unauthorized network activity.
[INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface as it processes external, potentially untrusted business logic (SOPs) to produce code.
Ingestion points: Untrusted data enters the agent context when reading plain-text SOPs or requirements in 'Step 1' of the workflow.
Boundary markers: The agent is instructed to follow strict EBNF grammar constraints and a non-Turing-complete instruction set (v0.1 blocks), which limits the execution scope of the generated output.
Capability inventory: The skill utilizes the orgscript CLI for formatting, validation, and exporting, as well as file modification for .orgs files.
Sanitization: The workflow relies on the orgscript validate and orgscript check tools to confirm the canonical AST shape and AST-level correctness before further processing or export.

OrgScript Engineer